Gatehouse defines 3 tools with clear names and reasonable descriptions. All tools have input schemas with typed parameters and descriptions. However, output schemas are not documented, error handling lacks recovery guidance, and parameter descriptions could be more detailed about constraints and formats. The tools follow verb_noun naming (run_sql, report_data_issue, gatehouse_whoami) and address distinct concerns, but descriptions are brief (50-100 chars) and lack context about when to use each tool or what happens on failure.

• Document output schemas for all tools. E.g., gatehouse_whoami returns {agent_id, permissions: [string], risk_tier}; run_sql returns {rows: [object], row_count, execution_time_ms}.
• Expand parameter descriptions with constraints: 'sql' → 'SQL SELECT/INSERT/UPDATE/DELETE query (max 10KB, no DDL, no PRAGMA)'; 'severity' → 'one of: LOW, MEDIUM, HIGH, CRITICAL'.
• Add error handling guidance to descriptions: 'run_sql may fail if: (1) syntax error → fix query; (2) permission denied → check agent scopes; (3) timeout → simplify query or reduce result set'.
• Increase tool descriptions to 100-200 chars. Include when to use: 'gatehouse_whoami: Call first to check your agent identity and data access permissions before attempting queries.'
• Document SQL injection and input validation in run_sql description: 'Queries are analyzed for policy compliance and SQL injection risk before execution. Parameterized queries recommended.'

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry